Lead Developer - GenAI & RAG Systems

Lead Developer – GenAI & RAG SystemsLocation: Austin, TX (Hybrid with 3 days onsite) Type: Contract Only local candidatesJob SummaryWe are seeking a highly skilled Lead Developer with strong expertise in Python, Generative AI (LLMs, RAG pipelines, Embeddings), and GCP Cloud Services. The ideal candidate will have hands-on experience in building production-grade AI/ML systems with UI integration, managing secure enterprise deployments, and ensuring scalability and compliance.Key ResponsibilitiesDesign, build, and deploy Retrieval-Augmented Generation (RAG) pipelines for enterprise GenAI solutionsDevelop scalable LLM-based applications using embeddings, vector databases, and prompt engineering best practicesWork with Azure Functions, Azure OpenAI, Azure ML, Cosmos DB, and Blob Storage for cloud-native implementationsBuild robust Python microservices for real-time AI inference and data processingIntegrate secure authentication mechanisms (SSO, OAuth, JWT) ensuring security and compliance standardsCollaborate with front-end engineers to build interactive UIs for AI workflowsLead and mentor junior developers in AI/ML engineering best practicesEnsure performance, fault tolerance, and observability in deployed applicationsRequired Skills & Experience8+ years of experience in software engineering, with at least 3+ years in AI/ML systemsExpertise in Python and hands-on experience with RAG pipelines, LLMs (GPT, Claude, LLaMA, etc.), and embedding modelsGCP stack: Vertex AI, Cloud Functions, Firestore, BigQueryDeep understanding of enterprise integrations including SSO, authentication, data privacy, and complianceExperience with vector databases like Pinecone, FAISS, Weaviate, or Azure Cognitive SearchFamiliarity with front-end/UI development frameworks (e.g. React, Streamlit, Flask for dashboards)Proven record of deploying production-grade AI applications with UI and backend integrationPreferred SkillsExperience with LangChain, LlamaIndex, or similar GenAI orchestration frameworksKnowledge of MLOps practices and tools (e.g., MLflow, Azure DevOps)Familiarity with CI/CD pipelines and containerization using Docker & Kubernetes